Sequentially choosing the most uncertain training question given previously chosen exemplars improves few-shot chain-of-thought accuracy by about 0.7 points on average over non-adaptive active prompting.
Association for Computational Linguistics (2019)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Power of Adaptation: Boosting In-Context Learning through Adaptive Prompting
Sequentially choosing the most uncertain training question given previously chosen exemplars improves few-shot chain-of-thought accuracy by about 0.7 points on average over non-adaptive active prompting.